1 Summary

This is an overview of data preparation for ‘8635.0 - Tourist Accommodation, Australia, 2015-16’ dataset from ABS.

2 ToDo

3 Data preparation

3.1 Raw data

Data are openly available. Unfortunately they can only be dowloaded in form of horribly designed spreadsheets:


Note the empty cells! Comment for them says:

not available for publication but included in totals where applicable, unless otherwise indicated

3.2 Data processing SA2 level

  • Monthly values of Guest Nights Occupied (GNO) were extracted
  • Empty cells are kept as missing data
  • Date is formated to 1st of the month
  • ‘Migratory - Offshore - Shipping’ SA2 is removed
  • Data are linked to spatial boundaries - unfortunately 2011 SA2s are used :/

4 Results SA2 level

4.1 Data structure

Final dataset consists of 11856 rows representing 12 observations (months) for 988 SA2s.

There are 8.597767710^{7} GNO in total.

4.2 Missing data

SA2s differ in how many months of data they have information on.

There are 419 with any values, out of which 351 have complete year of monthly data and
569 with no values. Additionally, there are other SA2s not present in the data which obviously will also have no values on accomodations.

Distribution of areas with and without data:

4.3 Yearly totals